Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 22600
    Prev
    Next
    INDEX
    Explanations

    phrases related to absence or insufficiency

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lack" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ń·
    -0.77
     Dug
    -0.62
     Steps
    -0.61
    selves
    -0.60
     Shades
    -0.60
     Springs
    -0.58
     Seal
    -0.58
     Circus
    -0.57
    imer
    -0.55
     Petra
    -0.55
    POSITIVE LOGITS
    lust
    1.57
    luster
    1.47
     thereof
    1.28
    ada
    1.20
    lessly
    0.98
    adas
    0.95
    iveness
    0.88
     of
    0.85
    ioned
    0.85
    phal
    0.84
    Activations Density 0.030%

    No Known Activations